refactor: add docs

magic_pdf/model/__init__.py

+from typing import Callable
+
+from abc import ABC, abstractmethod
+
+from magic_pdf.data.data_reader_writer import DataWriter
+from magic_pdf.data.dataset import Dataset
+from magic_pdf.pipe.operators import PipeResult
+
+
 __use_inside_model__ = True
 __model_mode__ = "full"
+
+
+class InferenceResultBase(ABC):
+
+    @abstractmethod
+    def __init__(self, inference_results: list, dataset: Dataset):
+        """Initialized method.
+
+        Args:
+            inference_results (list): the inference result generated by model
+            dataset (Dataset): the dataset related with model inference result
+        """
+        self._infer_res = inference_results
+        self._dataset = dataset
+
+    @abstractmethod
+    def draw_model(self, file_path: str) -> None:
+        """Draw model inference result.
+
+        Args:
+            file_path (str): the output file path
+        """
+        pass
+
+    @abstractmethod
+    def dump_model(self, writer: DataWriter, file_path: str):
+        """Dump model inference result to file.
+
+        Args:
+            writer (DataWriter): writer handle
+            file_path (str): the location of target file
+        """
+        pass
+
+    @abstractmethod
+    def get_infer_res(self):
+        """Get the inference result.
+
+        Returns:
+            list: the inference result generated by model
+        """
+        pass
+
+    @abstractmethod
+    def apply(self, proc: Callable, *args, **kwargs):
+        """Apply callable method which.
+
+        Args:
+            proc (Callable): invoke proc as follows:
+                proc(inference_result, *args, **kwargs)
+
+        Returns:
+            Any: return the result generated by proc
+        """
+        pass
+
+    @abstractmethod
+    def pipe_auto_mode(
+        self,
+        imageWriter: DataWriter,
+        start_page_id=0,
+        end_page_id=None,
+        debug_mode=False,
+        lang=None,
+    ) -> PipeResult:
+        """Post-proc the model inference result.
+            step1: classify the dataset type
+            step2: based the result of step1, using `pipe_txt_mode` or `pipe_ocr_mode`
+
+        Args:
+            imageWriter (DataWriter): the image writer handle
+            start_page_id (int, optional): Defaults to 0. Let user select some pages He/She want to process
+            end_page_id (int, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
+            debug_mode (bool, optional): Defaults to False. will dump more log if enabled
+            lang (str, optional): Defaults to None.
+
+        Returns:
+            PipeResult: the result
+        """
+        pass
+
+    @abstractmethod
+    def pipe_txt_mode(
+        self,
+        imageWriter: DataWriter,
+        start_page_id=0,
+        end_page_id=None,
+        debug_mode=False,
+        lang=None,
+    ) -> PipeResult:
+        """Post-proc the model inference result, Extract the text using the
+        third library, such as `pymupdf`
+
+        Args:
+            imageWriter (DataWriter): the image writer handle
+            start_page_id (int, optional): Defaults to 0. Let user select some pages He/She want to process
+            end_page_id (int, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
+            debug_mode (bool, optional): Defaults to False. will dump more log if enabled
+            lang (str, optional): Defaults to None.
+
+        Returns:
+            PipeResult: the result
+        """
+        pass
+
+    @abstractmethod
+    def pipe_ocr_mode(
+        self,
+        imageWriter: DataWriter,
+        start_page_id=0,
+        end_page_id=None,
+        debug_mode=False,
+        lang=None,
+    ) -> PipeResult:
+        pass

magic_pdf/model/operators.py

@@ -10,9 +10,10 @@ from magic_pdf.filter import classify
 from magic_pdf.libs.draw_bbox import draw_model_bbox
 from magic_pdf.pdf_parse_union_core_v2 import pdf_parse_union
 from magic_pdf.pipe.operators import PipeResult
+from magic_pdf.model import InferenceResultBase
 
 
-class InferenceResult:
+class InferenceResult(InferenceResultBase):
     def __init__(self, inference_results: list, dataset: Dataset):
         """Initialized method.
 
@@ -52,7 +53,7 @@ class InferenceResult:
         """Get the inference result.
 
         Returns:
-            list[dict]: the inference result generated by model
+            list: the inference result generated by model
         """
         return self._infer_res
 
@@ -83,9 +84,9 @@ class InferenceResult:
         Args:
             imageWriter (DataWriter): the image writer handle
             start_page_id (int, optional): Defaults to 0. Let user select some pages He/She want to process
-            end_page_id (_type_, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
+            end_page_id (int, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
             debug_mode (bool, optional): Defaults to False. will dump more log if enabled
-            lang (_type_, optional): Defaults to None.
+            lang (str, optional): Defaults to None.
 
         Returns:
             PipeResult: the result
@@ -116,9 +117,9 @@ class InferenceResult:
         Args:
             imageWriter (DataWriter): the image writer handle
             start_page_id (int, optional): Defaults to 0. Let user select some pages He/She want to process
-            end_page_id (_type_, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
+            end_page_id (int, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
             debug_mode (bool, optional): Defaults to False. will dump more log if enabled
-            lang (_type_, optional): Defaults to None.
+            lang (str, optional): Defaults to None.
 
         Returns:
             PipeResult: the result
@@ -153,9 +154,9 @@ class InferenceResult:
         Args:
             imageWriter (DataWriter): the image writer handle
             start_page_id (int, optional): Defaults to 0. Let user select some pages He/She want to process
-            end_page_id (_type_, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
+            end_page_id (int, optional):  Defaults to the last page index of dataset. Let user select some pages He/She want to process
             debug_mode (bool, optional): Defaults to False. will dump more log if enabled
-            lang (_type_, optional): Defaults to None.
+            lang (str, optional): Defaults to None.
 
         Returns:
             PipeResult: the result

next_docs/en/api.rst

@@ -7,3 +7,5 @@
    api/read_api
    api/schemas
    api/io
+   api/pipe_operators
+   api/model_operators
\ No newline at end of file

next_docs/en/api/model_operators.rst

+
+Model Api
+==========
+
+.. autoclass:: magic_pdf.model.InferenceResultBase
+   :members:
+   :inherited-members:
+   :show-inheritance:

next_docs/en/api/pipe_operators.rst

+
+
+Pipeline Api
+=============
+
+.. autoclass:: magic_pdf.pipe.operators.PipeResult
+   :members:
+   :inherited-members:
+   :show-inheritance:
\ No newline at end of file

next_docs/en/conf.py

@@ -114,7 +114,7 @@ autodoc_mock_imports = [
     'sentencepiece',
     'vllm.cuda_utils',
     'vllm._C',
-    'numpy',
+    # 'numpy',
     'tqdm',
 ]